© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60824
    Prev
    Next
    INDEX
    Explanations

    reliable publish

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ver
    0.38
     O
    0.35
     Just
    0.34
     Salts
    0.34
     जग
    0.34
     Anch
    0.34
    .~
    0.33
    alink
    0.33
    ihal
    0.33
     వ
    0.32
    POSITIVE LOGITS
     наде
    1.17
     reliable
    1.04
     reliably
    1.02
     Reliable
    0.93
    Reli
    0.93
    可靠
    0.91
     publish
    0.90
    reliable
    0.88
    Publish
    0.86
     publicación
    0.86
    Activations Density 0.008%

    No Known Activations